Pre-Training on Dynamic Graph Neural Networks
This work addresses the need for effective pre-training in dynamic graph neural networks for applications like social network analysis, but it is incremental as it builds on existing pre-training methods by adding dynamic evolution features.
The paper tackled the problem of pre-training graph neural networks without considering network evolution, and proposed PT-DGNN, a method that learns structure, semantics, and evolution features through dynamic attributed graph generation tasks, achieving the best results on link prediction fine-tuning tasks across three realistic dynamic network datasets.
The pre-training on the graph neural network model can learn the general features of large-scale networks or networks of the same type by self-supervised methods, which allows the model to work even when node labels are missing. However, the existing pre-training methods do not take network evolution into consideration. This paper proposes a pre-training method on dynamic graph neural networks (PT-DGNN), which uses dynamic attributed graph generation tasks to simultaneously learn the structure, semantics, and evolution features of the graph. The method includes two steps: 1) dynamic sub-graph sampling, and 2) pre-training with dynamic attributed graph generation task. Comparative experiments on three realistic dynamic network datasets show that the proposed method achieves the best results on the link prediction fine-tuning task.